TIGeR generates a rough 3D object prior from a text caption and refines it with 2D-3D attention to reconstruct hand-object interactions without pre-defined templates.
In: CVPR (2023)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TIGeR: Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction
TIGeR generates a rough 3D object prior from a text caption and refines it with 2D-3D attention to reconstruct hand-object interactions without pre-defined templates.